diff --git "a/config.json" "b/config.json" --- "a/config.json" +++ "b/config.json" @@ -1,12 +1,16 @@ { - "_name_or_path": "meta-llama/Meta-Llama-3.1-70B", + "_name_or_path": "meta-llama/Meta-Llama-3.1-70B-Instruct", "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, - "eos_token_id": 128001, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, @@ -20,7 +24,7 @@ "pretraining_tp": 1, "quant_config": { "model.layers.0.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -44,7 +48,7 @@ ] }, "model.layers.0.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -68,7 +72,7 @@ ] }, "model.layers.0.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -92,7 +96,7 @@ ] }, "model.layers.0.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -116,7 +120,7 @@ ] }, "model.layers.0.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -140,7 +144,7 @@ ] }, "model.layers.0.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -164,7 +168,7 @@ ] }, "model.layers.0.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -188,7 +192,7 @@ ] }, "model.layers.1.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -212,7 +216,7 @@ ] }, "model.layers.1.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -236,7 +240,7 @@ ] }, "model.layers.1.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -260,7 +264,7 @@ ] }, "model.layers.1.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -284,7 +288,7 @@ ] }, "model.layers.1.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -308,7 +312,7 @@ ] }, "model.layers.1.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -332,7 +336,7 @@ ] }, "model.layers.1.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -356,7 +360,7 @@ ] }, "model.layers.10.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -380,7 +384,7 @@ ] }, "model.layers.10.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -404,7 +408,7 @@ ] }, "model.layers.10.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -428,7 +432,7 @@ ] }, "model.layers.10.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -452,7 +456,7 @@ ] }, "model.layers.10.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -476,7 +480,7 @@ ] }, "model.layers.10.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -500,7 +504,7 @@ ] }, "model.layers.10.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -524,7 +528,7 @@ ] }, "model.layers.11.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -548,7 +552,7 @@ ] }, "model.layers.11.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -572,7 +576,7 @@ ] }, "model.layers.11.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -596,7 +600,7 @@ ] }, "model.layers.11.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -620,7 +624,7 @@ ] }, "model.layers.11.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -644,7 +648,7 @@ ] }, "model.layers.11.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -668,7 +672,7 @@ ] }, "model.layers.11.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -692,7 +696,7 @@ ] }, "model.layers.12.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -716,7 +720,7 @@ ] }, "model.layers.12.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -740,7 +744,7 @@ ] }, "model.layers.12.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -764,7 +768,7 @@ ] }, "model.layers.12.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -788,7 +792,7 @@ ] }, "model.layers.12.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -812,7 +816,7 @@ ] }, "model.layers.12.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -836,7 +840,7 @@ ] }, "model.layers.12.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -860,7 +864,7 @@ ] }, "model.layers.13.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -884,7 +888,7 @@ ] }, "model.layers.13.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -908,7 +912,7 @@ ] }, "model.layers.13.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -932,7 +936,7 @@ ] }, "model.layers.13.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -956,7 +960,7 @@ ] }, "model.layers.13.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -980,7 +984,7 @@ ] }, "model.layers.13.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1004,7 +1008,7 @@ ] }, "model.layers.13.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1028,7 +1032,7 @@ ] }, "model.layers.14.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1052,7 +1056,7 @@ ] }, "model.layers.14.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1076,7 +1080,7 @@ ] }, "model.layers.14.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1100,7 +1104,7 @@ ] }, "model.layers.14.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1124,7 +1128,7 @@ ] }, "model.layers.14.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1148,7 +1152,7 @@ ] }, "model.layers.14.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1172,7 +1176,7 @@ ] }, "model.layers.14.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1196,7 +1200,7 @@ ] }, "model.layers.15.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1220,7 +1224,7 @@ ] }, "model.layers.15.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1244,7 +1248,7 @@ ] }, "model.layers.15.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1268,7 +1272,7 @@ ] }, "model.layers.15.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1292,7 +1296,7 @@ ] }, "model.layers.15.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1316,7 +1320,7 @@ ] }, "model.layers.15.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1340,7 +1344,7 @@ ] }, "model.layers.15.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1364,7 +1368,7 @@ ] }, "model.layers.16.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1388,7 +1392,7 @@ ] }, "model.layers.16.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1412,7 +1416,7 @@ ] }, "model.layers.16.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1436,7 +1440,7 @@ ] }, "model.layers.16.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1460,7 +1464,7 @@ ] }, "model.layers.16.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1484,7 +1488,7 @@ ] }, "model.layers.16.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1508,7 +1512,7 @@ ] }, "model.layers.16.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1532,7 +1536,7 @@ ] }, "model.layers.17.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1556,7 +1560,7 @@ ] }, "model.layers.17.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1580,7 +1584,7 @@ ] }, "model.layers.17.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1604,7 +1608,7 @@ ] }, "model.layers.17.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1628,7 +1632,7 @@ ] }, "model.layers.17.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1652,7 +1656,7 @@ ] }, "model.layers.17.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1676,7 +1680,7 @@ ] }, "model.layers.17.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1700,7 +1704,7 @@ ] }, "model.layers.18.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1724,7 +1728,7 @@ ] }, "model.layers.18.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1748,7 +1752,7 @@ ] }, "model.layers.18.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1772,7 +1776,7 @@ ] }, "model.layers.18.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1796,7 +1800,7 @@ ] }, "model.layers.18.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1820,7 +1824,7 @@ ] }, "model.layers.18.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1844,7 +1848,7 @@ ] }, "model.layers.18.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1868,7 +1872,7 @@ ] }, "model.layers.19.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1892,7 +1896,7 @@ ] }, "model.layers.19.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1916,7 +1920,7 @@ ] }, "model.layers.19.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1940,7 +1944,7 @@ ] }, "model.layers.19.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1964,7 +1968,7 @@ ] }, "model.layers.19.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -1988,7 +1992,7 @@ ] }, "model.layers.19.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2012,7 +2016,7 @@ ] }, "model.layers.19.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2036,7 +2040,7 @@ ] }, "model.layers.2.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2060,7 +2064,7 @@ ] }, "model.layers.2.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2084,7 +2088,7 @@ ] }, "model.layers.2.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2108,7 +2112,7 @@ ] }, "model.layers.2.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2132,7 +2136,7 @@ ] }, "model.layers.2.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2156,7 +2160,7 @@ ] }, "model.layers.2.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2180,7 +2184,7 @@ ] }, "model.layers.2.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2204,7 +2208,7 @@ ] }, "model.layers.20.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2228,7 +2232,7 @@ ] }, "model.layers.20.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2252,7 +2256,7 @@ ] }, "model.layers.20.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2276,7 +2280,7 @@ ] }, "model.layers.20.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2300,7 +2304,7 @@ ] }, "model.layers.20.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2324,7 +2328,7 @@ ] }, "model.layers.20.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2348,7 +2352,7 @@ ] }, "model.layers.20.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2372,7 +2376,7 @@ ] }, "model.layers.21.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2396,7 +2400,7 @@ ] }, "model.layers.21.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2420,7 +2424,7 @@ ] }, "model.layers.21.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2444,7 +2448,7 @@ ] }, "model.layers.21.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2468,7 +2472,7 @@ ] }, "model.layers.21.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2492,7 +2496,7 @@ ] }, "model.layers.21.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2516,7 +2520,7 @@ ] }, "model.layers.21.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2540,7 +2544,7 @@ ] }, "model.layers.22.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2564,7 +2568,7 @@ ] }, "model.layers.22.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2588,7 +2592,7 @@ ] }, "model.layers.22.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2612,7 +2616,7 @@ ] }, "model.layers.22.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2636,7 +2640,7 @@ ] }, "model.layers.22.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2660,7 +2664,7 @@ ] }, "model.layers.22.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2684,7 +2688,7 @@ ] }, "model.layers.22.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2708,7 +2712,7 @@ ] }, "model.layers.23.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2732,7 +2736,7 @@ ] }, "model.layers.23.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2756,7 +2760,7 @@ ] }, "model.layers.23.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2780,7 +2784,7 @@ ] }, "model.layers.23.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2804,7 +2808,7 @@ ] }, "model.layers.23.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2828,7 +2832,7 @@ ] }, "model.layers.23.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2852,7 +2856,7 @@ ] }, "model.layers.23.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2876,7 +2880,7 @@ ] }, "model.layers.24.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2900,7 +2904,7 @@ ] }, "model.layers.24.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2924,7 +2928,7 @@ ] }, "model.layers.24.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2948,7 +2952,7 @@ ] }, "model.layers.24.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2972,7 +2976,7 @@ ] }, "model.layers.24.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -2996,7 +3000,7 @@ ] }, "model.layers.24.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3020,7 +3024,7 @@ ] }, "model.layers.24.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3044,7 +3048,7 @@ ] }, "model.layers.25.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3068,7 +3072,7 @@ ] }, "model.layers.25.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3092,7 +3096,7 @@ ] }, "model.layers.25.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3116,7 +3120,7 @@ ] }, "model.layers.25.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3140,7 +3144,7 @@ ] }, "model.layers.25.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3164,7 +3168,7 @@ ] }, "model.layers.25.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3188,7 +3192,7 @@ ] }, "model.layers.25.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3212,7 +3216,7 @@ ] }, "model.layers.26.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3236,7 +3240,7 @@ ] }, "model.layers.26.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3260,7 +3264,7 @@ ] }, "model.layers.26.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3284,7 +3288,7 @@ ] }, "model.layers.26.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3308,7 +3312,7 @@ ] }, "model.layers.26.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3332,7 +3336,7 @@ ] }, "model.layers.26.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3356,7 +3360,7 @@ ] }, "model.layers.26.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3380,7 +3384,7 @@ ] }, "model.layers.27.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3404,7 +3408,7 @@ ] }, "model.layers.27.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3428,7 +3432,7 @@ ] }, "model.layers.27.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3452,7 +3456,7 @@ ] }, "model.layers.27.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3476,7 +3480,7 @@ ] }, "model.layers.27.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3500,7 +3504,7 @@ ] }, "model.layers.27.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3524,7 +3528,7 @@ ] }, "model.layers.27.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3548,7 +3552,7 @@ ] }, "model.layers.28.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3572,7 +3576,7 @@ ] }, "model.layers.28.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3596,7 +3600,7 @@ ] }, "model.layers.28.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3620,7 +3624,7 @@ ] }, "model.layers.28.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3644,7 +3648,7 @@ ] }, "model.layers.28.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3668,7 +3672,7 @@ ] }, "model.layers.28.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3692,7 +3696,7 @@ ] }, "model.layers.28.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3716,7 +3720,7 @@ ] }, "model.layers.29.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3740,7 +3744,7 @@ ] }, "model.layers.29.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3764,7 +3768,7 @@ ] }, "model.layers.29.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3788,7 +3792,7 @@ ] }, "model.layers.29.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3812,7 +3816,7 @@ ] }, "model.layers.29.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3836,7 +3840,7 @@ ] }, "model.layers.29.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3860,7 +3864,7 @@ ] }, "model.layers.29.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3884,7 +3888,7 @@ ] }, "model.layers.3.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3908,7 +3912,7 @@ ] }, "model.layers.3.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3932,7 +3936,7 @@ ] }, "model.layers.3.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3956,7 +3960,7 @@ ] }, "model.layers.3.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -3980,7 +3984,7 @@ ] }, "model.layers.3.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4004,7 +4008,7 @@ ] }, "model.layers.3.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4028,7 +4032,7 @@ ] }, "model.layers.3.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4052,7 +4056,7 @@ ] }, "model.layers.30.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4076,7 +4080,7 @@ ] }, "model.layers.30.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4100,7 +4104,7 @@ ] }, "model.layers.30.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4124,7 +4128,7 @@ ] }, "model.layers.30.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4148,7 +4152,7 @@ ] }, "model.layers.30.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4172,7 +4176,7 @@ ] }, "model.layers.30.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4196,7 +4200,7 @@ ] }, "model.layers.30.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4220,7 +4224,7 @@ ] }, "model.layers.31.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4244,7 +4248,7 @@ ] }, "model.layers.31.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4268,7 +4272,7 @@ ] }, "model.layers.31.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4292,7 +4296,7 @@ ] }, "model.layers.31.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4316,7 +4320,7 @@ ] }, "model.layers.31.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4340,7 +4344,7 @@ ] }, "model.layers.31.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4364,7 +4368,7 @@ ] }, "model.layers.31.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4388,7 +4392,7 @@ ] }, "model.layers.32.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4412,7 +4416,7 @@ ] }, "model.layers.32.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4436,7 +4440,7 @@ ] }, "model.layers.32.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4460,7 +4464,7 @@ ] }, "model.layers.32.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4484,7 +4488,7 @@ ] }, "model.layers.32.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4508,7 +4512,7 @@ ] }, "model.layers.32.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4532,7 +4536,7 @@ ] }, "model.layers.32.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4556,7 +4560,7 @@ ] }, "model.layers.33.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4580,7 +4584,7 @@ ] }, "model.layers.33.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4604,7 +4608,7 @@ ] }, "model.layers.33.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4628,7 +4632,7 @@ ] }, "model.layers.33.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4652,7 +4656,7 @@ ] }, "model.layers.33.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4676,7 +4680,7 @@ ] }, "model.layers.33.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4700,7 +4704,7 @@ ] }, "model.layers.33.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4724,7 +4728,7 @@ ] }, "model.layers.34.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4748,7 +4752,7 @@ ] }, "model.layers.34.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4772,7 +4776,7 @@ ] }, "model.layers.34.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4796,7 +4800,7 @@ ] }, "model.layers.34.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4820,7 +4824,7 @@ ] }, "model.layers.34.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4844,7 +4848,7 @@ ] }, "model.layers.34.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4868,7 +4872,7 @@ ] }, "model.layers.34.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4892,7 +4896,7 @@ ] }, "model.layers.35.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4916,7 +4920,7 @@ ] }, "model.layers.35.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4940,7 +4944,7 @@ ] }, "model.layers.35.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4964,7 +4968,7 @@ ] }, "model.layers.35.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -4988,7 +4992,7 @@ ] }, "model.layers.35.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5012,7 +5016,7 @@ ] }, "model.layers.35.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5036,7 +5040,7 @@ ] }, "model.layers.35.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5060,7 +5064,7 @@ ] }, "model.layers.36.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5084,7 +5088,7 @@ ] }, "model.layers.36.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5108,7 +5112,7 @@ ] }, "model.layers.36.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5132,7 +5136,7 @@ ] }, "model.layers.36.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5156,7 +5160,7 @@ ] }, "model.layers.36.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5180,7 +5184,7 @@ ] }, "model.layers.36.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5204,7 +5208,7 @@ ] }, "model.layers.36.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5228,7 +5232,7 @@ ] }, "model.layers.37.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5252,7 +5256,7 @@ ] }, "model.layers.37.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5276,7 +5280,7 @@ ] }, "model.layers.37.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5300,7 +5304,7 @@ ] }, "model.layers.37.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5324,7 +5328,7 @@ ] }, "model.layers.37.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5348,7 +5352,7 @@ ] }, "model.layers.37.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5372,7 +5376,7 @@ ] }, "model.layers.37.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5396,7 +5400,7 @@ ] }, "model.layers.38.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5420,7 +5424,7 @@ ] }, "model.layers.38.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5444,7 +5448,7 @@ ] }, "model.layers.38.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5468,7 +5472,7 @@ ] }, "model.layers.38.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5492,7 +5496,7 @@ ] }, "model.layers.38.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5516,7 +5520,7 @@ ] }, "model.layers.38.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5540,7 +5544,7 @@ ] }, "model.layers.38.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5564,7 +5568,7 @@ ] }, "model.layers.39.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5588,7 +5592,7 @@ ] }, "model.layers.39.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5612,7 +5616,7 @@ ] }, "model.layers.39.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5636,7 +5640,7 @@ ] }, "model.layers.39.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5660,7 +5664,7 @@ ] }, "model.layers.39.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5684,7 +5688,7 @@ ] }, "model.layers.39.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5708,7 +5712,7 @@ ] }, "model.layers.39.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5732,7 +5736,7 @@ ] }, "model.layers.4.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5756,7 +5760,7 @@ ] }, "model.layers.4.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5780,7 +5784,7 @@ ] }, "model.layers.4.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5804,7 +5808,7 @@ ] }, "model.layers.4.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5828,7 +5832,7 @@ ] }, "model.layers.4.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5852,7 +5856,7 @@ ] }, "model.layers.4.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5876,7 +5880,7 @@ ] }, "model.layers.4.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5900,7 +5904,7 @@ ] }, "model.layers.40.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5924,7 +5928,7 @@ ] }, "model.layers.40.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5948,7 +5952,7 @@ ] }, "model.layers.40.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5972,7 +5976,7 @@ ] }, "model.layers.40.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -5996,7 +6000,7 @@ ] }, "model.layers.40.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6020,7 +6024,7 @@ ] }, "model.layers.40.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6044,7 +6048,7 @@ ] }, "model.layers.40.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6068,7 +6072,7 @@ ] }, "model.layers.41.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6092,7 +6096,7 @@ ] }, "model.layers.41.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6116,7 +6120,7 @@ ] }, "model.layers.41.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6140,7 +6144,7 @@ ] }, "model.layers.41.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6164,7 +6168,7 @@ ] }, "model.layers.41.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6188,7 +6192,7 @@ ] }, "model.layers.41.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6212,7 +6216,7 @@ ] }, "model.layers.41.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6236,7 +6240,7 @@ ] }, "model.layers.42.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6260,7 +6264,7 @@ ] }, "model.layers.42.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6284,7 +6288,7 @@ ] }, "model.layers.42.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6308,7 +6312,7 @@ ] }, "model.layers.42.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6332,7 +6336,7 @@ ] }, "model.layers.42.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6356,7 +6360,7 @@ ] }, "model.layers.42.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6380,7 +6384,7 @@ ] }, "model.layers.42.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6404,7 +6408,7 @@ ] }, "model.layers.43.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6428,7 +6432,7 @@ ] }, "model.layers.43.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6452,7 +6456,7 @@ ] }, "model.layers.43.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6476,7 +6480,7 @@ ] }, "model.layers.43.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6500,7 +6504,7 @@ ] }, "model.layers.43.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6524,7 +6528,7 @@ ] }, "model.layers.43.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6548,7 +6552,7 @@ ] }, "model.layers.43.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6572,7 +6576,7 @@ ] }, "model.layers.44.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6596,7 +6600,7 @@ ] }, "model.layers.44.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6620,7 +6624,7 @@ ] }, "model.layers.44.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6644,7 +6648,7 @@ ] }, "model.layers.44.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6668,7 +6672,7 @@ ] }, "model.layers.44.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6692,7 +6696,7 @@ ] }, "model.layers.44.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6716,7 +6720,7 @@ ] }, "model.layers.44.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6740,7 +6744,7 @@ ] }, "model.layers.45.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6764,7 +6768,7 @@ ] }, "model.layers.45.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6788,7 +6792,7 @@ ] }, "model.layers.45.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6812,7 +6816,7 @@ ] }, "model.layers.45.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6836,7 +6840,7 @@ ] }, "model.layers.45.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6860,7 +6864,7 @@ ] }, "model.layers.45.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6884,7 +6888,7 @@ ] }, "model.layers.45.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6908,7 +6912,7 @@ ] }, "model.layers.46.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6932,7 +6936,7 @@ ] }, "model.layers.46.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6956,7 +6960,7 @@ ] }, "model.layers.46.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -6980,7 +6984,7 @@ ] }, "model.layers.46.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7004,7 +7008,7 @@ ] }, "model.layers.46.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7028,7 +7032,7 @@ ] }, "model.layers.46.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7052,7 +7056,7 @@ ] }, "model.layers.46.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7076,7 +7080,7 @@ ] }, "model.layers.47.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7100,7 +7104,7 @@ ] }, "model.layers.47.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7124,7 +7128,7 @@ ] }, "model.layers.47.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7148,7 +7152,7 @@ ] }, "model.layers.47.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7172,7 +7176,7 @@ ] }, "model.layers.47.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7196,7 +7200,7 @@ ] }, "model.layers.47.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7220,7 +7224,7 @@ ] }, "model.layers.47.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7244,7 +7248,7 @@ ] }, "model.layers.48.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7268,7 +7272,7 @@ ] }, "model.layers.48.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7292,7 +7296,7 @@ ] }, "model.layers.48.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7316,7 +7320,7 @@ ] }, "model.layers.48.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7340,7 +7344,7 @@ ] }, "model.layers.48.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7364,7 +7368,7 @@ ] }, "model.layers.48.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7388,7 +7392,7 @@ ] }, "model.layers.48.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7412,7 +7416,7 @@ ] }, "model.layers.49.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7436,7 +7440,7 @@ ] }, "model.layers.49.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7460,7 +7464,7 @@ ] }, "model.layers.49.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7484,7 +7488,7 @@ ] }, "model.layers.49.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7508,7 +7512,7 @@ ] }, "model.layers.49.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7532,7 +7536,7 @@ ] }, "model.layers.49.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7556,7 +7560,7 @@ ] }, "model.layers.49.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7580,7 +7584,7 @@ ] }, "model.layers.5.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7604,7 +7608,7 @@ ] }, "model.layers.5.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7628,7 +7632,7 @@ ] }, "model.layers.5.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7652,7 +7656,7 @@ ] }, "model.layers.5.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7676,7 +7680,7 @@ ] }, "model.layers.5.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7700,7 +7704,7 @@ ] }, "model.layers.5.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7724,7 +7728,7 @@ ] }, "model.layers.5.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7748,7 +7752,7 @@ ] }, "model.layers.50.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7772,7 +7776,7 @@ ] }, "model.layers.50.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7796,7 +7800,7 @@ ] }, "model.layers.50.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7820,7 +7824,7 @@ ] }, "model.layers.50.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7844,7 +7848,7 @@ ] }, "model.layers.50.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7868,7 +7872,7 @@ ] }, "model.layers.50.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7892,7 +7896,7 @@ ] }, "model.layers.50.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7916,7 +7920,7 @@ ] }, "model.layers.51.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7940,7 +7944,7 @@ ] }, "model.layers.51.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7964,7 +7968,7 @@ ] }, "model.layers.51.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -7988,7 +7992,7 @@ ] }, "model.layers.51.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8012,7 +8016,7 @@ ] }, "model.layers.51.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8036,7 +8040,7 @@ ] }, "model.layers.51.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8060,7 +8064,7 @@ ] }, "model.layers.51.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8084,7 +8088,7 @@ ] }, "model.layers.52.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8108,7 +8112,7 @@ ] }, "model.layers.52.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8132,7 +8136,7 @@ ] }, "model.layers.52.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8156,7 +8160,7 @@ ] }, "model.layers.52.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8180,7 +8184,7 @@ ] }, "model.layers.52.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8204,7 +8208,7 @@ ] }, "model.layers.52.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8228,7 +8232,7 @@ ] }, "model.layers.52.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8252,7 +8256,7 @@ ] }, "model.layers.53.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8276,7 +8280,7 @@ ] }, "model.layers.53.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8300,7 +8304,7 @@ ] }, "model.layers.53.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8324,7 +8328,7 @@ ] }, "model.layers.53.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8348,7 +8352,7 @@ ] }, "model.layers.53.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8372,7 +8376,7 @@ ] }, "model.layers.53.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8396,7 +8400,7 @@ ] }, "model.layers.53.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8420,7 +8424,7 @@ ] }, "model.layers.54.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8444,7 +8448,7 @@ ] }, "model.layers.54.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8468,7 +8472,7 @@ ] }, "model.layers.54.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8492,7 +8496,7 @@ ] }, "model.layers.54.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8516,7 +8520,7 @@ ] }, "model.layers.54.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8540,7 +8544,7 @@ ] }, "model.layers.54.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8564,7 +8568,7 @@ ] }, "model.layers.54.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8588,7 +8592,7 @@ ] }, "model.layers.55.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8612,7 +8616,7 @@ ] }, "model.layers.55.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8636,7 +8640,7 @@ ] }, "model.layers.55.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8660,7 +8664,7 @@ ] }, "model.layers.55.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8684,7 +8688,7 @@ ] }, "model.layers.55.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8708,7 +8712,7 @@ ] }, "model.layers.55.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8732,7 +8736,7 @@ ] }, "model.layers.55.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8756,7 +8760,7 @@ ] }, "model.layers.56.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8780,7 +8784,7 @@ ] }, "model.layers.56.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8804,7 +8808,7 @@ ] }, "model.layers.56.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8828,7 +8832,7 @@ ] }, "model.layers.56.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8852,7 +8856,7 @@ ] }, "model.layers.56.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8876,7 +8880,7 @@ ] }, "model.layers.56.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8900,7 +8904,7 @@ ] }, "model.layers.56.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8924,7 +8928,7 @@ ] }, "model.layers.57.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8948,7 +8952,7 @@ ] }, "model.layers.57.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8972,7 +8976,7 @@ ] }, "model.layers.57.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -8996,7 +9000,7 @@ ] }, "model.layers.57.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9020,7 +9024,7 @@ ] }, "model.layers.57.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9044,7 +9048,7 @@ ] }, "model.layers.57.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9068,7 +9072,7 @@ ] }, "model.layers.57.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9092,7 +9096,7 @@ ] }, "model.layers.58.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9116,7 +9120,7 @@ ] }, "model.layers.58.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9140,7 +9144,7 @@ ] }, "model.layers.58.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9164,7 +9168,7 @@ ] }, "model.layers.58.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9188,7 +9192,7 @@ ] }, "model.layers.58.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9212,7 +9216,7 @@ ] }, "model.layers.58.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9236,7 +9240,7 @@ ] }, "model.layers.58.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9260,7 +9264,7 @@ ] }, "model.layers.59.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9284,7 +9288,7 @@ ] }, "model.layers.59.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9308,7 +9312,7 @@ ] }, "model.layers.59.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9332,7 +9336,7 @@ ] }, "model.layers.59.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9356,7 +9360,7 @@ ] }, "model.layers.59.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9380,7 +9384,7 @@ ] }, "model.layers.59.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9404,7 +9408,7 @@ ] }, "model.layers.59.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9428,7 +9432,7 @@ ] }, "model.layers.6.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9452,7 +9456,7 @@ ] }, "model.layers.6.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9476,7 +9480,7 @@ ] }, "model.layers.6.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9500,7 +9504,7 @@ ] }, "model.layers.6.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9524,7 +9528,7 @@ ] }, "model.layers.6.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9548,7 +9552,7 @@ ] }, "model.layers.6.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9572,7 +9576,7 @@ ] }, "model.layers.6.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9596,7 +9600,7 @@ ] }, "model.layers.60.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9620,7 +9624,7 @@ ] }, "model.layers.60.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9644,7 +9648,7 @@ ] }, "model.layers.60.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9668,7 +9672,7 @@ ] }, "model.layers.60.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9692,7 +9696,7 @@ ] }, "model.layers.60.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9716,7 +9720,7 @@ ] }, "model.layers.60.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9740,7 +9744,7 @@ ] }, "model.layers.60.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9764,7 +9768,7 @@ ] }, "model.layers.61.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9788,7 +9792,7 @@ ] }, "model.layers.61.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9812,7 +9816,7 @@ ] }, "model.layers.61.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9836,7 +9840,7 @@ ] }, "model.layers.61.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9860,7 +9864,7 @@ ] }, "model.layers.61.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9884,7 +9888,7 @@ ] }, "model.layers.61.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9908,7 +9912,7 @@ ] }, "model.layers.61.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9932,7 +9936,7 @@ ] }, "model.layers.62.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9956,7 +9960,7 @@ ] }, "model.layers.62.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -9980,7 +9984,7 @@ ] }, "model.layers.62.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10004,7 +10008,7 @@ ] }, "model.layers.62.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10028,7 +10032,7 @@ ] }, "model.layers.62.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10052,7 +10056,7 @@ ] }, "model.layers.62.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10076,7 +10080,7 @@ ] }, "model.layers.62.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10100,7 +10104,7 @@ ] }, "model.layers.63.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10124,7 +10128,7 @@ ] }, "model.layers.63.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10148,7 +10152,7 @@ ] }, "model.layers.63.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10172,7 +10176,7 @@ ] }, "model.layers.63.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10196,7 +10200,7 @@ ] }, "model.layers.63.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10220,7 +10224,7 @@ ] }, "model.layers.63.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10244,7 +10248,7 @@ ] }, "model.layers.63.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10268,7 +10272,7 @@ ] }, "model.layers.64.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10292,7 +10296,7 @@ ] }, "model.layers.64.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10316,7 +10320,7 @@ ] }, "model.layers.64.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10340,7 +10344,7 @@ ] }, "model.layers.64.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10364,7 +10368,7 @@ ] }, "model.layers.64.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10388,7 +10392,7 @@ ] }, "model.layers.64.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10412,7 +10416,7 @@ ] }, "model.layers.64.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10436,7 +10440,7 @@ ] }, "model.layers.65.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10460,7 +10464,7 @@ ] }, "model.layers.65.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10484,7 +10488,7 @@ ] }, "model.layers.65.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10508,7 +10512,7 @@ ] }, "model.layers.65.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10532,7 +10536,7 @@ ] }, "model.layers.65.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10556,7 +10560,7 @@ ] }, "model.layers.65.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10580,7 +10584,7 @@ ] }, "model.layers.65.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10604,7 +10608,7 @@ ] }, "model.layers.66.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10628,7 +10632,7 @@ ] }, "model.layers.66.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10652,7 +10656,7 @@ ] }, "model.layers.66.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10676,7 +10680,7 @@ ] }, "model.layers.66.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10700,7 +10704,7 @@ ] }, "model.layers.66.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10724,7 +10728,7 @@ ] }, "model.layers.66.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10748,7 +10752,7 @@ ] }, "model.layers.66.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10772,7 +10776,7 @@ ] }, "model.layers.67.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10796,7 +10800,7 @@ ] }, "model.layers.67.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10820,7 +10824,7 @@ ] }, "model.layers.67.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10844,7 +10848,7 @@ ] }, "model.layers.67.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10868,7 +10872,7 @@ ] }, "model.layers.67.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10892,7 +10896,7 @@ ] }, "model.layers.67.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10916,7 +10920,7 @@ ] }, "model.layers.67.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10940,7 +10944,7 @@ ] }, "model.layers.68.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10964,7 +10968,7 @@ ] }, "model.layers.68.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -10988,7 +10992,7 @@ ] }, "model.layers.68.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11012,7 +11016,7 @@ ] }, "model.layers.68.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11036,7 +11040,7 @@ ] }, "model.layers.68.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11060,7 +11064,7 @@ ] }, "model.layers.68.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11084,7 +11088,7 @@ ] }, "model.layers.68.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11108,7 +11112,7 @@ ] }, "model.layers.69.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11132,7 +11136,7 @@ ] }, "model.layers.69.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11156,7 +11160,7 @@ ] }, "model.layers.69.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11180,7 +11184,7 @@ ] }, "model.layers.69.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11204,7 +11208,7 @@ ] }, "model.layers.69.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11228,7 +11232,7 @@ ] }, "model.layers.69.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11252,7 +11256,7 @@ ] }, "model.layers.69.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11276,7 +11280,7 @@ ] }, "model.layers.7.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11300,7 +11304,7 @@ ] }, "model.layers.7.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11324,7 +11328,7 @@ ] }, "model.layers.7.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11348,7 +11352,7 @@ ] }, "model.layers.7.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11372,7 +11376,7 @@ ] }, "model.layers.7.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11396,7 +11400,7 @@ ] }, "model.layers.7.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11420,7 +11424,7 @@ ] }, "model.layers.7.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11444,7 +11448,7 @@ ] }, "model.layers.70.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11468,7 +11472,7 @@ ] }, "model.layers.70.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11492,7 +11496,7 @@ ] }, "model.layers.70.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11516,7 +11520,7 @@ ] }, "model.layers.70.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11540,7 +11544,7 @@ ] }, "model.layers.70.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11564,7 +11568,7 @@ ] }, "model.layers.70.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11588,7 +11592,7 @@ ] }, "model.layers.70.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11612,7 +11616,7 @@ ] }, "model.layers.71.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11636,7 +11640,7 @@ ] }, "model.layers.71.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11660,7 +11664,7 @@ ] }, "model.layers.71.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11684,7 +11688,7 @@ ] }, "model.layers.71.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11708,7 +11712,7 @@ ] }, "model.layers.71.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11732,7 +11736,7 @@ ] }, "model.layers.71.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11756,7 +11760,7 @@ ] }, "model.layers.71.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11780,7 +11784,7 @@ ] }, "model.layers.72.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11804,7 +11808,7 @@ ] }, "model.layers.72.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11828,7 +11832,7 @@ ] }, "model.layers.72.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11852,7 +11856,7 @@ ] }, "model.layers.72.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11876,7 +11880,7 @@ ] }, "model.layers.72.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11900,7 +11904,7 @@ ] }, "model.layers.72.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11924,7 +11928,7 @@ ] }, "model.layers.72.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11948,7 +11952,7 @@ ] }, "model.layers.73.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11972,7 +11976,7 @@ ] }, "model.layers.73.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -11996,7 +12000,7 @@ ] }, "model.layers.73.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12020,7 +12024,7 @@ ] }, "model.layers.73.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12044,7 +12048,7 @@ ] }, "model.layers.73.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12068,7 +12072,7 @@ ] }, "model.layers.73.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12092,7 +12096,7 @@ ] }, "model.layers.73.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12116,7 +12120,7 @@ ] }, "model.layers.74.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12140,7 +12144,7 @@ ] }, "model.layers.74.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12164,7 +12168,7 @@ ] }, "model.layers.74.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12188,7 +12192,7 @@ ] }, "model.layers.74.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12212,7 +12216,7 @@ ] }, "model.layers.74.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12236,7 +12240,7 @@ ] }, "model.layers.74.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12260,7 +12264,7 @@ ] }, "model.layers.74.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12284,7 +12288,7 @@ ] }, "model.layers.75.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12308,7 +12312,7 @@ ] }, "model.layers.75.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12332,7 +12336,7 @@ ] }, "model.layers.75.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12356,7 +12360,7 @@ ] }, "model.layers.75.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12380,7 +12384,7 @@ ] }, "model.layers.75.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12404,7 +12408,7 @@ ] }, "model.layers.75.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12428,7 +12432,7 @@ ] }, "model.layers.75.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12452,7 +12456,7 @@ ] }, "model.layers.76.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12476,7 +12480,7 @@ ] }, "model.layers.76.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12500,7 +12504,7 @@ ] }, "model.layers.76.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12524,7 +12528,7 @@ ] }, "model.layers.76.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12548,7 +12552,7 @@ ] }, "model.layers.76.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12572,7 +12576,7 @@ ] }, "model.layers.76.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12596,7 +12600,7 @@ ] }, "model.layers.76.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12620,7 +12624,7 @@ ] }, "model.layers.77.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12644,7 +12648,7 @@ ] }, "model.layers.77.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12668,7 +12672,7 @@ ] }, "model.layers.77.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12692,7 +12696,7 @@ ] }, "model.layers.77.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12716,7 +12720,7 @@ ] }, "model.layers.77.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12740,7 +12744,7 @@ ] }, "model.layers.77.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12764,7 +12768,7 @@ ] }, "model.layers.77.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12788,7 +12792,7 @@ ] }, "model.layers.78.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12812,7 +12816,7 @@ ] }, "model.layers.78.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12836,7 +12840,7 @@ ] }, "model.layers.78.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12860,7 +12864,7 @@ ] }, "model.layers.78.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12884,7 +12888,7 @@ ] }, "model.layers.78.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12908,7 +12912,7 @@ ] }, "model.layers.78.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12932,7 +12936,7 @@ ] }, "model.layers.78.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12956,7 +12960,7 @@ ] }, "model.layers.79.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -12980,7 +12984,7 @@ ] }, "model.layers.79.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -13004,7 +13008,7 @@ ] }, "model.layers.79.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -13028,7 +13032,7 @@ ] }, "model.layers.79.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -13052,7 +13056,7 @@ ] }, "model.layers.79.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -13076,7 +13080,7 @@ ] }, "model.layers.79.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -13100,7 +13104,7 @@ ] }, "model.layers.79.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -13124,7 +13128,7 @@ ] }, "model.layers.8.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -13148,7 +13152,7 @@ ] }, "model.layers.8.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -13172,7 +13176,7 @@ ] }, "model.layers.8.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -13196,7 +13200,7 @@ ] }, "model.layers.8.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -13220,7 +13224,7 @@ ] }, "model.layers.8.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -13244,7 +13248,7 @@ ] }, "model.layers.8.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -13268,7 +13272,7 @@ ] }, "model.layers.8.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -13292,7 +13296,7 @@ ] }, "model.layers.9.mlp.down_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -13316,7 +13320,7 @@ ] }, "model.layers.9.mlp.gate_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -13340,7 +13344,7 @@ ] }, "model.layers.9.mlp.up_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -13364,7 +13368,7 @@ ] }, "model.layers.9.self_attn.k_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -13388,7 +13392,7 @@ ] }, "model.layers.9.self_attn.o_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -13412,7 +13416,7 @@ ] }, "model.layers.9.self_attn.q_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1, @@ -13436,7 +13440,7 @@ ] }, "model.layers.9.self_attn.v_proj": { - "bias": false, + "bias": null, "enable_norm": true, "enable_perm": true, "group_num": 1,